2026-10-10T04:14:19Z
https://api.figshare.com/v2/oai
oai:figshare.com:article/33903662
2026-09-17T17:26:40Z
category_146
category_272
category_734
category_106
portal_5
item_type_3
month_year_09_2026
<p>Physiological deep learning methods.</p>
Haoran Wu (785718)
Timothy Tettey Nartey (25037504)
Guangjun Wan (25037507)
Yugang Wang (317500)
Linli Xu (560183)
Xun Zhou (240352)
Space Science
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
Science Policy
provided foundational contributions
operational design domain
harmonised operational definitions
driving scenarios relevant
identify methodological limitations
final search completed
div >< p
th </ sup
level 3 datasets
examine performance metrics
conditional automated driving
review </ p
driver state detection
state detection
conditional automation
identify driver
guided search
state monitoring
state constructs
driver state
validation strategies
timely transition
time feasibility
study suggests
studies published
road validation
review presents
review aims
representative sampling
reporting inconsistencies
prisma 2020
previous studies
language publications
ieee xplore
future development
finally advises
examined driver
also calls
<div><p>SAE Level 3 automated driving systems assume full control of the dynamic driving task within their operational design domain. Ensuring a safe and timely transition from automated to manual driving therefore necessitates continuous monitoring and assessment of driver state. This review presents a synthesis of 85 studies published mainly between 2021 and 2025. A PRISMA 2020-guided search was conducted in ScienceDirect, Web of Science, SpringerLink and IEEE Xplore, with the final search completed on 15<sup>th</sup> September 2025. Only English-language publications that examined driver-state detection, recognition or assessment in driving scenarios relevant to conditional automation were considered. Studies published before 2021 were excluded, unless they provided foundational contributions. This review was not registered. This review aims to (1) identify driver-state constructs that have been investigated in conditional automated driving, examining how they are defined and operationalized; (2) characterize sensing modalities used for driver-state monitoring; (3) evaluate computational approaches including multimodal fusion used in previous studies; (4) examine performance metrics, validation strategies and real-time feasibility; (5) identify methodological limitations, reporting inconsistencies and priorities for future development and deployment. This study suggests the standardisation of Level 3 datasets. It also calls for harmonised operational definitions and more representative sampling. It finally advises the performance of more longitudinal on-road validation. This work was supported by the National Natural Science Foundation of China.</p></div>
2026-09-17T17:26:18Z
Dataset
Dataset
10.1371/journal.pone.0358700.t006
https://figshare.com/articles/dataset/_p_Physiological_deep_learning_methods_p_/33903662
CC BY 4.0